Implicit Alternatives and the Local Power of Test Statistics

Russell Davidson and James MacKinnon ()

Econometrica, 1987, vol. 55, issue 6, pages 1305-29

Abstract: The local power of test statistics is analyzed by considering sequences of data-generating processes (DGPs) that approach the null hypothesis without necessarily satisfying the alternative. The three classical test statistics-LR, Wald, and LM-are shown to tend asymptot ically to the same random variable under all such sequences. The powe r of these statistics depends on the null, the alternative, and the sequence of DGPs in a geometrically intuitive way. This implies that, for any statistic that is asymptotically chi-squared under the null, there exists an "implicit alternative hypothesis" against which that statistic will have highest power. Copyright 1987 by The Econometric Society.

Date: 1987
View citations in EconPapers

Downloads: (external link)
http://links.jstor.org/sici?sici=0012-9682%2819871 ... O%3B2-E&origin=repec full text (application/pdf)
Access to full text is restricted to JSTOR subscribers. See http://www.jstor.org for details.

Related works:
Working Paper: Implicit alternatives and the local power of test statistics (1985)
Working Paper: Implicit Alternatives and the Local Power of Test Statistics (1984)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:ecm:emetrp:v:55:y:1987:i:6:p:1305-29

Ordering information: This journal article can be ordered from
http://www.blackwell ... mb.asp?ref=0012-9682

Access Statistics for this article

Econometrica is edited by Stephen Morris

More articles in Econometrica from Econometric Society
Contact information at EDIRC.
Series data maintained by Christopher F. Baum ().